Re: [PATCH 5/9] x86/percpu/64: Use relative percpu offsets
From: Uros Bizjak
Date: Tue Oct 24 2023 - 08:44:08 EST
On Mon, Oct 23, 2023 at 11:17 PM Brian Gerst <brgerst@xxxxxxxxx> wrote:
>
> The percpu section is currently linked at virtual address 0, because
> older compilers hardcoded the stack protector canary value at a fixed
> offset from the start of the GS segment. Now that the canary is a
> normal percpu variable, the percpu section can be linked normally.
> This means that x86-64 will calculate percpu offsets like most other
> architectures, as the delta between the initial percpu address and the
> dynamically allocated memory.
>
> Signed-off-by: Brian Gerst <brgerst@xxxxxxxxx>
> ---
> arch/x86/kernel/head_64.S | 6 ------
> arch/x86/kernel/setup_percpu.c | 12 ++----------
> arch/x86/kernel/vmlinux.lds.S | 24 +-----------------------
> arch/x86/tools/relocs.c | 10 +++-------
> arch/x86/xen/xen-head.S | 6 ------
> init/Kconfig | 2 +-
> 6 files changed, 7 insertions(+), 53 deletions(-)
>
> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
> index f2453eb38417..b35f74e58dd7 100644
> --- a/arch/x86/kernel/head_64.S
> +++ b/arch/x86/kernel/head_64.S
> @@ -72,14 +72,8 @@ SYM_CODE_START_NOALIGN(startup_64)
>
> /* Setup GSBASE to allow stack canary access for C code */
> movl $MSR_GS_BASE, %ecx
> -#ifdef CONFIG_SMP
> - leaq __per_cpu_load(%rip), %rdx
> - movl %edx, %eax
> - shrq $32, %rdx
> -#else
> xorl %eax, %eax
> xorl %edx, %edx
> -#endif
> wrmsr
>
> call startup_64_setup_env
> diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
> index 2c97bf7b56ae..8707dd07b9ce 100644
> --- a/arch/x86/kernel/setup_percpu.c
> +++ b/arch/x86/kernel/setup_percpu.c
> @@ -23,18 +23,10 @@
> #include <asm/cpumask.h>
> #include <asm/cpu.h>
>
> -#ifdef CONFIG_X86_64
> -#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
> -#else
> -#define BOOT_PERCPU_OFFSET 0
> -#endif
> -
> -DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
> +DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
> EXPORT_PER_CPU_SYMBOL(this_cpu_off);
>
> -unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
> - [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
> -};
> +unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
> EXPORT_SYMBOL(__per_cpu_offset);
>
> /*
> diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
> index c87dc8de2084..8d8eb4d9ff9d 100644
> --- a/arch/x86/kernel/vmlinux.lds.S
> +++ b/arch/x86/kernel/vmlinux.lds.S
> @@ -102,12 +102,6 @@ jiffies = jiffies_64;
> PHDRS {
> text PT_LOAD FLAGS(5); /* R_E */
> data PT_LOAD FLAGS(6); /* RW_ */
> -#ifdef CONFIG_X86_64
> -#ifdef CONFIG_SMP
> - percpu PT_LOAD FLAGS(6); /* RW_ */
> -#endif
> - init PT_LOAD FLAGS(7); /* RWE */
> -#endif
> note PT_NOTE FLAGS(0); /* ___ */
> }
>
> @@ -223,21 +217,7 @@ SECTIONS
> __init_begin = .; /* paired with __init_end */
> }
>
> -#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
> - /*
> - * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
> - * output PHDR, so the next output section - .init.text - should
> - * start another segment - init.
> - */
> - PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
> - ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
> - "per-CPU data too large - increase CONFIG_PHYSICAL_START")
> -#endif
> -
> INIT_TEXT_SECTION(PAGE_SIZE)
> -#ifdef CONFIG_X86_64
> - :init
> -#endif
>
> /*
> * Section for code used exclusively before alternatives are run. All
> @@ -367,9 +347,7 @@ SECTIONS
> EXIT_DATA
> }
>
> -#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
> PERCPU_SECTION(INTERNODE_CACHE_BYTES)
> -#endif
>
> . = ALIGN(PAGE_SIZE);
>
> @@ -507,7 +485,7 @@ SECTIONS
> * Per-cpu symbols which need to be offset from __per_cpu_load
> * for the boot processor.
> */
> -#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
> +#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x)
> INIT_PER_CPU(gdt_page);
> INIT_PER_CPU(irq_stack_backing_store);
>
> diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
> index 3ccd9d4fcf9c..01efbfdd3eb3 100644
> --- a/arch/x86/tools/relocs.c
> +++ b/arch/x86/tools/relocs.c
> @@ -815,12 +815,7 @@ static void percpu_init(void)
> */
> static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
> {
> - int shndx = sym_index(sym);
> -
> - return (shndx == per_cpu_shndx) &&
> - strcmp(symname, "__init_begin") &&
> - strcmp(symname, "__per_cpu_load") &&
> - strncmp(symname, "init_per_cpu_", 13);
> + return 0;
> }
>
>
> @@ -1043,7 +1038,8 @@ static int cmp_relocs(const void *va, const void *vb)
>
> static void sort_relocs(struct relocs *r)
> {
> - qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
> + if (r->count)
> + qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
> }
>
> static int write32(uint32_t v, FILE *f)
> diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
> index 9ce0d9d268bb..c1d9c92b417a 100644
> --- a/arch/x86/xen/xen-head.S
> +++ b/arch/x86/xen/xen-head.S
> @@ -57,14 +57,8 @@ SYM_CODE_START(startup_xen)
> * the per cpu areas are set up.
> */
> movl $MSR_GS_BASE,%ecx
> -#ifdef CONFIG_SMP
> - leaq __per_cpu_load(%rip), %rdx
> - movl %edx, %eax
> - shrq $32, %rdx
> -#else
> xorl %eax, %eax
> xorl %edx, %edx
> -#endif
> wrmsr
>
> mov %rsi, %rdi
Again, please note there is another access to $MSR_GS_BASE in
/arch/x86/platform/pvh/head.S that should be reviewed.
Uros.
> diff --git a/init/Kconfig b/init/Kconfig
> index 6d35728b94b2..1af31b23e376 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1718,7 +1718,7 @@ config KALLSYMS_ALL
> config KALLSYMS_ABSOLUTE_PERCPU
> bool
> depends on KALLSYMS
> - default X86_64 && SMP
> + default n
>
> config KALLSYMS_BASE_RELATIVE
> bool
> --
> 2.41.0
>